spec-product-prd

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary function is local file manipulation (reading and writing markdown files) within a specific project directory structure. It does not perform network requests or execute shell commands outside of standard workflow transitions.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because it processes content from external files (solution.md, raw.md) which could contain untrusted instructions. However, this is an inherent part of its documentation purpose.
  • Ingestion points: Reads content from {FEATURE_DIR}/requirements/solution.md, {FEATURE_DIR}/requirements/raw.md, and project/memory/glossary.md.
  • Boundary markers: The skill does not explicitly use boundary markers or XML tags to isolate the content of the input files during the PRD generation prompt.
  • Capability inventory: The skill has permissions to write to the local filesystem (prd.md) and chain to the using-aisdlc skill.
  • Sanitization: No explicit sanitization or filtering of the input file content is implemented before it is processed by the AI.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 08:32 AM